LATIDIA · Robótica

Urano: construyendo la infraestructura de simulación de próxima generación para la IA incorporada

arXiv: 2609.24815v1Tipo de anuncio: nuevo Resumen: La simulación escalable es esencial para la generación de datos de robots, la capacitación en políticas, la evaluación y la iteración segura, pero la interacción en el mundo real es costosa y el simulador convencional

La noticia

arXiv:2609.24815v1 Announce Type: new Abstract: Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and conventional simulators require labor-intensive construction. We present Uranus, a data-driven robot simulator built around a joint-trajectory-conditioned autoregressive diffusion model. Uranus offers three key capabilities: (1) streaming, open-ended rollout, which receives future joint-position trajectories online and autoregressively generates one latent frame per step, corresponding to four RGB frames, without a fixed horizon; (2) low-latency generation, achieving 24 FPS after inference optimization; and (3) scalable, extensible robot control, providing a unified interface for synchronized multi-view generation across diverse robot embodiments and camera configurations. We conduct comprehensive quantitative